Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

He stared at the irises, their purple hues mirroring the bruises beneath his eyes. Liam hadn't shaved in days. He hadn't eaten properly either. The kitchen was a mess, mirroring the chaos inside him. The flowers, delivered without a card, sat on the table.

He moved toward them, slowly, as if wading through something thick and viscous. They were beautiful, yes, but their beauty felt like a taunt. Like a reminder of the world he could no longer reach.

He reached out, his fingers brushing the cool petals. A sudden wave of nausea washed over him. He stumbled back, the scent of the flowers becoming a suffocating presence. He backed away from the flowers and slumped against the wall, defeated.

Emotion: depressed

Cluster: Sadness / Despair
PC1 (Valence): -2.06 Negative
PC2 (Disposition): -1.08

Role in Research

This story is one of 1,000 stories generated for the emotion depressed. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 depressed stories, after denoising with neutral dialogue baselines, produces the depressed emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the depressed vector is projected through the unembedding matrix.

Promoted:
😞0.417
每天0.353
无法0.330
own0.311
😔0.309
Suppressed:
de-0.492
B-0.393
P-0.352
l-0.310
!-0.307